Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to lists and items prioritized within those lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stro
    -0.18
    à¸Ńะ
    -0.16
    ensa
    -0.16
    ãĥ©ãĥĥãĤ¯
    -0.16
    eah
    -0.16
    gili
    -0.16
    racÃŃ
    -0.15
    sov
    -0.15
    onis
    -0.14
    rage
    -0.14
    POSITIVE LOGITS
     amongst
    0.29
     priority
    0.29
     among
    0.29
    Priority
    0.28
     included
    0.26
     Priority
    0.25
    priority
    0.25
     Included
    0.25
     Among
    0.25
     listed
    0.25
    Act Density 0.145%

    No Known Activations